ucb_agentic_ai

Lecture 05: Coding Agents and AI for Vulnerability Detection

Link to lecture recording on YouTube

Date: 2025-03-03

Speaker: Charles Sutton

Speaker’s social profile: Website / Company Profile / Google Scholar / GitHub / LinkedIn / X (Twitter)

Education:

Work:

Notes

Coding Agents

Speaker’s definition of LLM agents:

LLM agents are multi-turn LLMs with tool use:

What this definition de-emphasizes:

Evaluation

Pre-history of LLM code evaluation:

Examples of evaluations of code-generation capabilities

AI for Computer Security

LLM Agents for Computer Security

[Incomplete, work in progress]

References

  1. Jacob Austin et al. Program Synthesis with Large Language Models. arXiv:2108.0773 [cs.PL]. 2021.

  2. Mark Chen et al. Evaluating Large Language Models Trained on Code. arXiv:2107.03374 [cs.LG]. 2021.